Abstract
The biometric identification is an important topic with applications in different fields. Among the different modalities, based-handwriting biometric is a very useful and extended modality, and the most known one is the signature. The use of handwritten texts is researched presenting a biometric system for identifying writers from their handwritten words. A set of feature-based graphometric information has been extracted from off-line handwritten words to implement an automatic biometric approach. Given the handwritten nature of the information and its great variability, a feature selection based on principal component analysis and neural network classifier has been proposed. A fusion block based on neural networks has been added in order to reduce the effect of the data variability due to an increase and stabilization of the accuracy. A dataset composed of 100 writers have been used for the experiments. A holdout cross-validation was applied and the accuracy reached between 99.80% and 100%.
Similar content being viewed by others
References
Puello AA (2007) La grafología y la personalidad. UOC, Barcelona
Romero CF, Travieso CM, Ferrer MA, Alonso JB (2009) Handwriting knowledge based on parameterization for writer identification. In: Proceedings of the European computing conference, vol 1, p 3
Varshney A, Puri S (2017). A survey on human personality identification on the basis of handwriting using ANN. In: 2017 international conference on inventive systems and control (ICISC), pp 1–6. https://doi.org/10.1109/icisc.2017.8068634
Al-Sanjary, OI, Ghazali S (2017) Classification of arabic writer based on clustering techniques. In: Recent trends in information and communication technology: proceedings of the 2nd international conference of reliable information and communication technology. vol 5. Springer, Berlin
Djeddi C, Souici-Meslati L, Ennaji A (2012) Writer recognition on arabic handwritten documents. In: 5th international conference image and signal processing, ICISP 2012, pp 493–501. https://doi.org/10.1007/978-3-642-31254-0_56
Tan GJ, Sulong G, Mohd Rahim MS (2015) Off-line text-independent writer recognition for chinese handwriting: a review. Jurnal Teknologi 75(2):39–50. https://doi.org/10.11113/jt.v75.4975
Jang W, Kim S, Kim Y, Lee EC (2017) Automated Verification method of korean word handwriting using geometric feature. In: Park J, Loia V, Yi G, Sung Y (eds) Advances in computer science and ubiquitous computing. CUTE 2017, CSA 2017. Lecture Notes in Electrical Engineering, vol 474. Springer, Berlin
Kumar R, Kumar Ravulakollu K, Bhat R (2017) Fuzzy-membership based writer identification from handwritten devnagari script. J Inf Process Syst 13(4):893–913. https://doi.org/10.3745/JIPS.02.0018
Brink AA, Smit J, Bulacu ML, Schomaker LRB (2012) Writer identification using directional ink-trace width measurements. Pattern Recogn 45(1):162–171. https://doi.org/10.1016/j.patcog.2011.07.005
Bertolini D, Oliveira LS, Justino E, Sabourin R (2013) Texture-based descriptors for writer identification and verification. Expert Syst Appl 40(6):2069–2080. https://doi.org/10.1016/j.eswa.2012.10.016
Jain R, Doermann D (2013) Writer identification using an alphabet of contour gradient descriptors. In: Language and multimedia processing laboratory, University of Maryland, College, Master Degree
Rajesh K, Bhabatosh C, Sharma JD (2014) A novel sparse model based forensic writer identification. Pattern Recogn Lett 35(1):105–112. https://doi.org/10.1016/j.patrec.2013.07.001
García-Hernández ZA (2012) Cálculo de Parámetros Basados en Ciencias Forenses para la Identificación de Escritores. B.ch. Thesis, ULPGC
Herrera EC (2008) Identificación del autor de un texto manuscrito. Ph.D. Thesis, Mexico
Miller JJ, Patterson RB, Gantz DT, Saunders CP, Walch MA, Buscaglia J (2017) A set of handwriting features for use in automated writer identification. J Forensic Sci 62:722–734. https://doi.org/10.1111/1556-4029.13345
Aubin V, Mora M (2017) A new descriptor for person identity verification based on handwritten strokes off-line analysis. Expert Syst Appl 89:241–253. https://doi.org/10.1016/j.eswa.2017.07.039
Bensefia A, Paquet T (2016) Writer verification based on a single handwriting word samples. EURASIP J Image Video Process. https://doi.org/10.1186/s13640-016-0139-0
Schomaker L (2007) Advances in writer identification and verification. In: Ninth international conference on document analysis and recognition (ICDAR), pp 1268–1273. https://doi.org/10.1109/icdar.2007.4377119
Faundez-Zanuy M, Elizondo DA, Ferrer-Ballester MA, Travieso CM (2007) Authentication of individuals using hand geometry biometrics: a neural network approach. Neural Process Lett 26(3):201–206
Santana O, Travieso CM, Ferrer MA, Alonso JB (2010) Writer identification based on graphology techniques. IEEE Aerosp Electron Syst Mag 25(6):35–42
Otsu N (1979) A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybernet 9(1):62–66
de Antón-Barberá F, Méndez-Baquero F (2005) Análisis de textos manuscritos, firmas y alteraciones documentales, Ed. Tirant lo blanch. 2005
Bozinovic RM, Srihari SN (1989) Off-line cursive script word recognition. IEEE Trans Pattern Anal Mach Intell 2:68–83
Duarte MA (2010) Documentología II. Licenciatura en Criminalística, Cátedra. Technical Report
Jolliffe IT (2002) Principal component analysis, 2nd edn. Springer, Berlin
Kruse Borgelt, Klawonn Moewes (2013) Computational intelligence: a methodological introduction by Steinbrecher. Springer, Held
Hyvärinen J, Karhunen EO (2001) Independent component analysis. Wiley-Interscience, New York
Arlot S, Celisse A (2010) A survey of cross-validation procedures for model selection. Stat Surv 4:40–79
Acknowledgements
This work has been supported by the Ministry of Economy and Competitiveness (TEC2016-77791-C4-234 1-R). In addition, authors would like to sincerely thank all the reviewers for their valuable comments, which have helped us to improve the quality of the paper.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no conflict of interest.
Rights and permissions
About this article
Cite this article
Vásquez, J.L., Ravelo-García, A.G., Alonso, J.B. et al. Writer identification approach by holistic graphometric features using off-line handwritten words. Neural Comput & Applic 32, 15733–15746 (2020). https://doi.org/10.1007/s00521-018-3461-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-018-3461-x